© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 12373
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts in relationships or choices

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     مشين
    -0.57
     nonUne
    -0.54
     <<<<<<<<<<<<<<
    -0.49
    Salta
    -0.48
    verter
    -0.47
    exitRule
    -0.47
     Rijks
    -0.46
     lut
    -0.46
    Παραπομπές
    -0.45
     '))
    -0.44
    POSITIVE LOGITS
    今回
    0.52
    这次
    0.51
    這次
    0.49
    今回は
    0.47
    这一次
    0.47
    今回の
    0.44
     costumbre
    0.42
     questão
    0.42
     оригіналу
    0.41
     diesmal
    0.40
    Activations Density 0.389%

    No Known Activations